The wafer map is obtained by testing each die in the wafer during semiconductor production for defects and marking the defective die. The classification of the wafer map can provide a basis information for problems that occur in the production process, thereby solving the problems and reducing the cost. Before classifying the wafer map, the most important thing is feature extraction. In addition to having a certain spatial pattern, the wafer map also has a lot of noise, which affects the process of feature extraction. When the traditional density-based spatial clustering of applications with noise(DBSCAN) algorithm is used for filtering, it needs to manually determine the value of Eps and MinPts parameters, and the selection of the parameters directly affects the accuracy of the clustering. Therefore, this paper proposes a filtering method based on the optimized DBSCAN clustering algorithm to automatically determine the parameters of the DBSCAN, which can solve the traditional drawbacks of manually parameters setting. This method selects a comprehensive index of cluster intra-cluster density and inter-cluster density to evaluate the optimal parameters. The experimental results show that the proposed algorithm can automatically and reasonably select better parameters and has a good clustering effect, which is also very helpful for subsequent feature extraction and classification.